Multi-Task Learning for Fatigue Detection and Face Recognition of Drivers via Tree-Style Space-Channel Attention Fusion Network

TL;DR

This paper introduces a novel tree-style multi-task learning model that efficiently combines fatigue detection and face recognition for drivers, utilizing shared features and attention mechanisms to improve performance in safety-critical driving scenarios.

Contribution

The paper proposes a new tree-style multi-task learning architecture with space-channel attention fusion, enabling effective joint driver fatigue detection and face recognition using single-task datasets.

Findings

Improved detection accuracy through space-channel attention mechanisms.

Effective multi-task learning with only single-task datasets.

Validated performance gains in driving safety applications.

Abstract

In driving scenarios, automobile active safety systems are increasingly incorporating deep learning technology. These systems typically need to handle multiple tasks simultaneously, such as detecting fatigue driving and recognizing the driver's identity. However, the traditional parallel-style approach of combining multiple single-task models tends to waste resources when dealing with similar tasks. Therefore, we propose a novel tree-style multi-task modeling approach for multi-task learning, which rooted at a shared backbone, more dedicated separate module branches are appended as the model pipeline goes deeper. Following the tree-style approach, we propose a multi-task learning model for simultaneously performing driver fatigue detection and face recognition for identifying a driver. This model shares a common feature extraction backbone module, with further separated feature extraction and classification module branches. The dedicated branches exploit and combine spatial and channel attention mechanisms to generate space-channel fused-attention enhanced features, leading to improved detection performance. As only single-task datasets are available, we introduce techniques including alternating updation and gradient accumulation for training our multi-task model using only the single-task datasets. The effectiveness of our tree-style multi-task learning model is verified through extensive validations.